Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends

Favorskaya, Margarita N.

doi:10.3390/electronics12092006

Cited by 14 publications

(4 citation statements)

References 120 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional SLAM systems often involve separate modules for localization and mapping, requiring intricate integration. Deep learning models employ end-to-end learning, enabling the system to grasp its location and construct a map simultaneously, simplifying the navigation process for more efficient underwater exploration [72,73]. Another advantage is the flexibility of deep learning in handling different sensors commonly used in underwater navigation, such as sonar, LiDAR, and cameras.…”

Section: Advantage Of Deep Learning Relative To the Conventional Methodsmentioning

confidence: 99%

Advancements in Underwater Navigation: Integrating Deep Learning and Sensor Technologies for Unmanned Underwater Vehicles

Merveille,

Jia,

2024

Preprint

View full text Add to dashboard Cite

Unmanned Underwater Vehicles (UUVs) are pivotal in ocean exploration, research, and various industrial activities such as marine mining and offshore engineering. However, traditional methods of navigating these vehicles face significant challenges, mainly due to the inefficacy of electromagnetic waves in water, leading to signal loss. To address these limitations, researchers are increasingly turned learning, an artificial intelligence technique capable of learning from data-enhancing underwater navigation, mainly through visual Simultaneous Localization and Mapping (SLAM). This paper explores integrating deep learning methodologies and sensor technologies to revolutionize underwater navigation for UUVs. Proprioceptive sensors, along with exteroceptive sensors, are crucial in accurately measuring and comprehending the underwater environment. Additionally, the paper provides detailed insights into the processes of underwater SLAM, camera-based underwater positioning systems, sonar systems for underwater navigation, and the utilization of Lidar in underwater navigation. Furthermore, it delves into applying deep learning techniques in underwater SLAM, offering a comprehensive understanding of the innovative processes driving advancements in underwater vehicle navigation. By leveraging these advancements, this research aims to improve underwater navigation systems' precision, reliability, and adaptability, thereby unlocking new frontiers in ocean exploration and industrial applications for UUVs.

show abstract

Section: Advantage Of Deep Learning Relative To the Conventional Methodsmentioning

confidence: 99%

Advancements in Underwater Navigation: Integrating Deep Learning and Sensor Technologies for Unmanned Underwater Vehicles

Merveille,

Jia,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…They particularly emphasize belief-space planning and deep reinforcement learning. In a related context, Zhang et al [27] and Favorskaya et al [59] delve into the role of deep learning in VSLAM approaches, investigating its applications in fundamental SLAM tasks such as pose optimization and mapping.…”

Section: Related Workmentioning

confidence: 99%

Survey of Deep Learning-Based Methods for FMCW Radar Odometry and Ego-Localization

Brune,

Meisen,

Pomp

2024

Applied Sciences

View full text Add to dashboard Cite

This paper provides an in-depth review of deep learning techniques to address the challenges of odometry and global ego-localization using frequency modulated continuous wave (FMCW) radar sensors. In particular, we focus on the prediction of odometry, which involves the determination of the ego-motion of a system by external sensors, and loop closure detection, which concentrates on the determination of the ego-position typically on an existing map. We initially emphasize the significance of these tasks in the context of radar sensors and underscore the motivations behind them. The subsequent sections delve into the practical implementation of deep learning approaches, strategically designed to effectively address the aforementioned challenges. We primarily focus on spinning and automotive radar configurations within the domain of autonomous driving. Additionally, we introduce publicly available datasets that have been instrumental in addressing these challenges and analyze the importance and struggles of current methods used for radar based odometry and localization. In conclusion, this paper highlights the distinctions between the addressed tasks and other radar perception applications, while also discussing their differences from challenges posed by alternative sensor modalities. The findings contribute to the ongoing discourse on advancing radar sensor capabilities through the application of deep learning methodologies, particularly in the context of enhancing odometry and ego-localization for autonomous driving applications.

show abstract

“…The segment anything model (SAM) [15] is a large-scale model in the field of computer vision, showcasing robust zero-shot performance across a range of segmentation tasks. The challenge lies in integrating SAM with VSLAM tasks in dynamic environments to overcome the universality limitation of general semantic SLAM, making it a challenging research topic [16]. To address this problem, we introduce SLM-SLAM, a VSLAM system based on a segmentation model designed for dynamic scenarios.…”

Section: Introductionmentioning

confidence: 99%

SLM-SLAM: a visual SLAM system based on segmented large-scale model in dynamic scenes and zero-shot conditions

Zhu,

Chen,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the real world, the presence of various dynamic objects can impact the localization accuracy of the majority of typical Visual Simultaneous Localization and Mapping (VSLAM) systems. Simultaneously, many dynamic VSLAM systems based on neural networks require pre-training for specific application scenarios. We present SLM-SLAM, the first VSLAM system that implements zero-shot processing of dynamic scenes. It achieves the capability to handle various dynamic objects without the necessity for pre-training, enabling straightforward adaptation to different application scenarios. Firstly, we designed an open-world semantic segmentation module based on a segmented large-scale model to acquire semantic information in the scene. Subsequently, we devised a label-based strategy for selecting feature points, jointly optimizing poses with the weighted labels provided by both semantic and geometric information. Finally, we refined the keyframe selection strategy of ORB-SLAM3 to prevent matching errors caused by an insufficient number of remaining static feature points in the scene. We conducted experiments on the TUM dataset, the KITTI dataset, and real world scenarios. The results indicate that in dynamic scenes, our SLM-SLAM significantly improves localization accuracy compared to ORB-SLAM3, and its performance is comparable to state-of-the-art dynamic VSLAM systems.

show abstract

Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends

Cited by 14 publications

References 120 publications

Advancements in Underwater Navigation: Integrating Deep Learning and Sensor Technologies for Unmanned Underwater Vehicles

Advancements in Underwater Navigation: Integrating Deep Learning and Sensor Technologies for Unmanned Underwater Vehicles

Survey of Deep Learning-Based Methods for FMCW Radar Odometry and Ego-Localization

SLM-SLAM: a visual SLAM system based on segmented large-scale model in dynamic scenes and zero-shot conditions

Contact Info

Product

Resources

About